MODEL HISTORY
gpt-oss-20b (high) 指标历史
gpt-oss-20b (high) 的公开评测事实历史,共 31 条观测、27 项指标;只记录来源变化,不插值、不合成本站总分。
怎样理解这份历史
每条记录对应来源快照中的一个原始指标。相同值重复抓取不会制造新记录;只有数值、临时状态或移除状态发生变化时才追加。首个快照是本站的可追溯起点,不代表该指标第一次对外发布。
Index、Elo、百分比等单位不能互相相减,也不会在这里合成为“综合总分”。
APPEND-ONLY FACTS
观测记录
按观测时间倒序;同日多项指标分别保留。
| 观测日期 | 基准 / 版本 | 指标 | 原始值 | 状态 |
|---|---|---|---|---|
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 12.3 秒 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输入价格 / 1M Tokenusd_per_1m_tokens | US$0.06 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 217.8 Token/s | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 10.0 秒 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Agentic Indexindex | 3.1 | 有效 | |
| Artificial Analysis agentic capability indexvunversioned | agentic capability indexindex | 3.1 | 有效 | |
| Artificial Analysis coding capability indexvunversioned | coding capability indexindex | 20.7 | 有效 | |
| Artificial Analysis finance capability indexvunversioned | finance capability indexindex | 9.2 | 有效 | |
| Artificial Analysis strategy capability indexvunversioned | strategy capability indexindex | 11.5 | 有效 | |
| Artificial Analysis legal capability indexvunversioned | legal capability indexindex | 9.4 | 有效 | |
| Artificial Analysis healthcare capability indexvunversioned | healthcare capability indexindex | 9.0 | 有效 | |
| Artificial Analysis engineering capability indexvunversioned | engineering capability indexindex | 20.4 | 有效 | |
| Artificial Analysis economics capability indexvunversioned | economics capability indexindex | 14.1 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Coding Indexindex | 20.7 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 上下文窗口tokens | 131,072 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | CritPtfraction | 1.4% | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 11.9 秒 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AAelo | 559 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 3.0% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GPQA Diamondfraction | 68.8% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 9.8% | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输入价格 / 1M Tokenusd_per_1m_tokens | US$0.05 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 14.9 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 30.7% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | -63.9 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输出价格 / 1M Tokenusd_per_1m_tokens | US$0.2 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 224.7 Token/s | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | SciCodefraction | 34.4% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 7.0% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Terminal-Bench v2.1fraction | 13.9% | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 9.7 秒 | 有效 |